G

Google: gemma-4-26b:free

gemma-4-26b:free
131.1K context32.8K outReasoningToolsVisionVideoStructuredStreamingSystem msg
Released Apr 3, 2026Updated Jun 20, 2026

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...

Mode chatTokenizer GemmaQuantization fp8google/gemma-4-26B-A4B-it

Pricing

Input price
$0.00/ 1M tokens
Output price
$0.00/ 1M tokens
Context window 131.1K tokensCompatible endpoints openai, geminiVendor Google

Uptime

Performance

Loading performance data...

Usage & Ranking

Loading usage...

Supported parameters

All providers = every upstream serving this model supports it. Some providers = depends on which upstream handles the request. Default = the value sent when you leave the parameter unset.

ParameterProvidersDefault
frequency_penaltyAll providers-
include_reasoningAll providers-
logit_biasSome providers-
logprobsAll providers-
max_tokensAll providers-
min_pSome providers-
presence_penaltyAll providers-
reasoningAll providers-
repetition_penaltyAll providers-
response_formatAll providers-
seedAll providers-
stopAll providers-
structured_outputsAll providers-
temperatureAll providers1
tool_choiceAll providers-
toolsAll providers-
top_kAll providers64
top_logprobsAll providers-
top_pAll providers0.95

Frequently asked questions

Similar models